Font Size: a A A

Highly Maneuvering Target Tracking Algorithm Based On Variable Structure Multiple-Model Algorithm

Posted on:2012-03-15Degree:MasterType:Thesis
Country:ChinaCandidate:X Y HuangFull Text:PDF
GTID:2178330335962756Subject:Pattern Recognition and Intelligent Systems
Abstract/Summary:PDF Full Text Request
Maneuvering target tracking is an important issue and has broad application prospects in the air early warning, battlefield surveillance, air traffic control, navigation systems and other civilian areas. With the rapid development of science and technology, the target mobility is growing fast, so the highly maneuvering target tracking has become the hot issues in this area. This paper focuses on the research of the highly maneuvering target tracking problem using the thought of variable structure multiple model, which is supported by the "11th Five-Year Plan" weapons and equipment pre-research project. The main work and achievements are as follows:First of all, an overview on the basic principles and elements of maneuvering target tracking is presented, which includes the target motion model and some commonly used filtering algorithms of maneuvering target tracking, and the analysis of the characteristics of these filtering algorithms.Secondly, the basic idea and principles of the variable structure multiple model (VSMM) algorithm by focusing on the researching of recursive adaptive model-set (RAMS) algorithm that is theoretical practical detailed analyzed. By researching the model set sequential likelihood ratio during filtering which is based on the analysis of model group switching (MGS) algorithm in RAMS, a theoretical "optimal" variable structure multiple model algorithm based on sequential likelihood ratio test (SLRT-VSMM) is presented. The simulation results show that the algorithm can improve the accuracy of tracking highly maneuvering target.Third, due to SLRT-VSMM no efficient advantage, this paper presents an unscented digraph switching variable structure multiple model algorithm by combining the directed graph (digraph) and unscented Kalman filter. This suboptimal algorithm not only improves the accuracy of tracking, but it decreases the computational burden as well. This algorithm is more suitable for the actual scene.Finally, this paper makes an exploring research on multiple target tracking with VSMM algorithm, and tentatively proposes a VSMMJPDA algorithm based on VSMM and joint probability data association (JPDA), since there isn't any literature researching on this area. The simulation result shows the feasibility of the algorithm.
Keywords/Search Tags:highly maneuvering target tracking, variable structure multiple model, sequential likelihood ratio test, directed graph, multiple target tracking
PDF Full Text Request
Related items